{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:54:51Z","timestamp":1776887691410,"version":"3.51.2"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100011993","name":"Robert Bosch","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011993","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230932","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning"],"prefix":"10.1109","author":[{"given":"Julia","family":"Wilkins","sequence":"first","affiliation":[{"name":"New York University,New York,USA"}]},{"given":"Sivan","family":"Ding","sequence":"additional","affiliation":[{"name":"New York University,New York,USA"}]},{"given":"Magdalena","family":"Fuentes","sequence":"additional","affiliation":[{"name":"New York University,New York,USA"}]},{"given":"Juan Pablo","family":"Bello","sequence":"additional","affiliation":[{"name":"New York University,New York,USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28 708","article-title":"Masked autoencoders that listen","volume":"35","author":"Huang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3506286"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095691"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2022-10961","article-title":"Mae-ast: Masked autoencoding audio spectrogram transformer","author":"Baade","year":"2022"},{"key":"ref6","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref7","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref8","first-page":"12 310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"International conference on machine learning","author":"Zbontar"},{"key":"ref9","article-title":"Vicreg: Variance-invariance-covariance regularization for self-supervised learning","author":"Bardes","year":"2022"},{"key":"ref10","article-title":"Multi-format contrastive learning of audio representations","author":"Wang","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415009"},{"key":"ref13","first-page":"2530","article-title":"Clar: Contrastive learning of auditory representations","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Al-Tahan"},{"key":"ref14","article-title":"Contrastive audio-visual masked autoencoder","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gong"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-391"},{"key":"ref16","article-title":"What should not be contrastive in contrastive learning","volume-title":"International Conference on Learning Representations","author":"Xiao"},{"key":"ref17","first-page":"47 309","article-title":"Focal: Contrastive learning for multimodal time-series sensing signals in factorized orthogonal latent space","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","article-title":"Self-supervised disentanglement by leveraging structure in data augmentations","volume-title":"Causal Representation Learning Workshop at NeurIPS 2023","author":"Eastwood"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890270"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447877"},{"key":"ref21","article-title":"Isolating sources of disentanglement in variational autoencoders","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref22","first-page":"2649","article-title":"Disentangling by factorising","volume-title":"International conference on machine learning","author":"Kim"},{"key":"ref23","first-page":"4402","article-title":"Disentangling disentanglement in variational autoencoders","volume-title":"International conference on machine learning","author":"Mathieu"},{"key":"ref24","article-title":"Learning disentangled audio representations through controlled synthesis","author":"Brima","year":"2024"},{"key":"ref25","first-page":"700","article-title":"Unsupervised disentanglement of pitch and timbre for isolated musical instrument sounds","author":"Luo","year":"2020","journal-title":"ISMIR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414059"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1561\/116.20240072"},{"key":"ref28","article-title":"Self-supervised multi-view learning for disentangled music audio representations","author":"Wilkins","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447473"},{"key":"ref30","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018"},{"key":"ref31","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","author":"Engel","year":"2017"},{"key":"ref32","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref33","article-title":"High-fidelity audio compression with improved rvqgan","author":"Kumar","year":"2023"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230932.pdf?arnumber=11230932","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:32:21Z","timestamp":1763191941000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230932\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230932","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}